EnigmaToM：利用实体状态的神经知识库提升LLM的心智理论推理能力
EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States
AI总结：
提出神经符号框架EnigmaToM，通过整合实体状态的神经知识库、迭代掩蔽机制与知识注入，显著提升不同规模LLM的心智理论推理能力，尤其在高阶推理场景中表现卓越。
摘要：
心智理论（Theory-of-Mind, ToM）即推断他人感知和心理状态的能力，是人类互动的基础，但对大语言模型（LLMs）仍具挑战。现有ToM推理方法虽在感知视角转换推理上显示出潜力，却往往过度依赖现成的LLM，降低了效率并限制了其在高阶ToM推理中的适用性。为解决这些问题，我们提出了EnigmaToM，一种新型神经符号框架，通过整合实体状态的神经知识库（Enigma）来增强ToM推理，该框架包含：(1) 受心理学启发的迭代掩蔽机制，以促进准确的视角转换；(2) 知识注入机制，以提取关键实体信息。Enigma生成实体状态的结构化知识，构建空间场景图以追踪各阶ToM的信念，并用细粒度实体状态细节丰富事件。在ToMi、HiToM和FANToM基准上的实验结果表明，EnigmaToM显著提升了不同规模LLM的ToM推理能力，尤其在高阶推理场景中表现卓越。
英文摘要：
Theory-of-Mind (ToM), the ability to infer others' perceptions and mental states, is fundamental to human interaction but remains challenging for Large Language Models (LLMs). While existing ToM reasoning methods show promise with reasoning via perceptual perspective-taking, they often rely excessively on off-the-shelf LLMs, reducing their efficiency and limiting their applicability to high-order ToM reasoning. To address these issues, we present EnigmaToM, a novel neuro-symbolic framework that enhances ToM reasoning by integrating a Neural Knowledge Base of entity states (Enigma) for (1) a psychology-inspired iterative masking mechanism that facilitates accurate perspective-taking and (2) knowledge injection that elicits key entity information. Enigma generates structured knowledge of entity states to build spatial scene graphs for belief tracking across various ToM orders and enrich events with fine-grained entity state details. Experimental results on ToMi, HiToM, and FANToM benchmarks show that EnigmaToM significantly improves ToM reasoning across LLMs of varying sizes, particularly excelling in high-order reasoning scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
